Master Assignment
AI in Healthcare: Solving real-world challenges in a regional hospital
Type: Master
Period: TBD
Student: (Unassigned)
If you are interested, please contact :
Background
Machine learning is rapidly transforming healthcare by enabling better diagnostics, personalized treatments, and more efficient clinical workflows. At our regional hospital, we collaborate closely with clinicians to apply AI to real-world challenges—ranging from predicting surgical risks to analyzing clinical notes and medical images. Our projects offer you the chance to work with healthcare data and contribute to meaningful innovations.
Projects
At the hospital, multiple departments are actively seeking students to join them in solving real-world healthcare challenges through Data Science. Whether you're interested in working with clinical text, medical images, or sensor-based time-series data, there's a project that aligns with your interests. Some projects even offer the opportunity to take your models all the way to real-world deployment.
Every project is supported by an active clinical stakeholder, ensuring you receive expert guidance and that your work remains grounded in real clinical needs. The list of available projects is regularly updated and will be shared with you on request. Below, you’ll find a selection of current projects to give you a sense of the available projects:
- Predicting complication-free recovery after hip fracture surgery using multimodal machine learning. Elderly patients often face complications after hip surgery. This project explores how machine learning can improve risk assessment and personalize treatment plans. A key challenge is integrating multiple data types—images, time-series, and tabular—into a single predictive model.
- Predicting Long-Term Outcomes After Bariatric Surgery Using Machine Learning. Knowledge about the individual long-term prognosis after bariatric surgery is limited. A machine learning model trained with time series data could improve prognosis prediction and help modify treatment to individual patient needs. A temporal model will be developed to predict future outcomes.
- Frailty Detection in Clinical Notes Using Natural Language Processing. This project focuses on developing a natural language processing system to identify early signs of frailty in older adults from unstructured clinical notes. By using techniques like named entity recognition and text classification, the model will extract indicators of physical, cognitive, and social decline.
Who we look for
We’re looking for motivated students who are eager to apply machine learning to real-world healthcare challenges in a clinical setting. You should have a solid foundation in machine learning and data science, and be comfortable working with Python. Furthermore, you enjoy interdisciplinary collaboration, and you can work independently.
What we offer
As a master’s student working on these projects, you will have the unique chance to work with real clinical data and impact local healthcare, and the projects can be tailored to your strengths and interests. You will be provided with access to local hardware to conduct experiments with clinical data in a safe environment.